The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses various shell commands to inspect the host environment and validate Docker configurations. Evidence includes calls to docker info, docker context ls, find, docker ps, docker build, and docker run for discovery and validation purposes.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon the contents of untrusted local files, creating a potential vector for instructions embedded in data to influence the agent's behavior. Ingestion points: Project files identified by find . -name "Dockerfile*" and find . -name "*compose*.yml". Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present when the agent processes these files. Capability inventory: The agent has the ability to execute docker build, docker run, and docker exec based on the content of these files. Sanitization: No sanitization or validation of the content of the Dockerfiles or Compose files is performed before processing.

docker-expert